Joint Representation Learning of Text and Knowledge for Knowledge Graph Completion

TL;DR

This paper introduces a unified embedding framework for text and knowledge graph data, improving the accuracy of knowledge graph completion by jointly learning representations of words, entities, and relations.

Contribution

It presents a novel joint embedding model that incorporates both knowledge graph structure and plain text into a shared semantic space, enhancing completion tasks.

Findings

Significant improvement in entity prediction accuracy

Enhanced relation prediction performance

Better relation classification results

Abstract

Joint representation learning of text and knowledge within a unified semantic space enables us to perform knowledge graph completion more accurately. In this work, we propose a novel framework to embed words, entities and relations into the same continuous vector space. In this model, both entity and relation embeddings are learned by taking knowledge graph and plain text into consideration. In experiments, we evaluate the joint learning model on three tasks including entity prediction, relation prediction and relation classification from text. The experiment results show that our model can significantly and consistently improve the performance on the three tasks as compared with other baselines.